Welcome to the Sentimental Analysis project! This machine learning endeavor aims to analyze and predict sentiments expressed in textual data. The project utilizes various natural language processing and machine learning techniques to classify sentiments as positive or negative. In-depth explorations include feature selection, data preparation, skewness handling, and model evaluation.
The primary objective of this project is to perform sentiment analysis and opinion mining on textual data. By utilizing machine learning algorithms and natural language processing techniques, we aim to classify sentiments as positive or negative. The project's focus is to understand and analyze public opinions from various sources, such as social media platforms like Twitter.
Understanding sentiments in text data holds immense potential, impacting areas such as:
- Marketing strategy formulation based on public sentiment.
- Enhancing customer satisfaction and loyalty.
- Predicting and managing public reactions during events and campaigns.
- Data Collection: Utilizing TensorFlow, we downloaded Amazon review datasets to train our models.
- Data Preprocessing: Tokenization, removing stop words, and converting text to lowercase.
- Sentiment Detection: Classification of sentiments into positive and negative categories.
- Machine Learning: Implementation of LSTM (Long Short-Term Memory) for sequence processing.
To run this project, ensure you have the following Python libraries installed:
- pandas, numpy, matplotlib, seaborn, scikit-learn, tensorflow.
- NLTK (Natural Language Toolkit)
You can install the required libraries using the following command:
pip install pandas numpy matplotlib seaborn scikit-learn nltk tensorflow- HTML/CSS
- Flask
- Godavarthi Sai Nikhil
- Mubashir Buhari
- Nichenametla Karthik Raja
We express our sincere gratitude to Dr. NISHTHA PHUTELA, who provided invaluable supervision during this project.
For inquiries, collaboration opportunities, or further information, please feel free to reach out to:
- Email: [email protected]
Thank you for joining us on this journey of sentiment analysis!